CN109599162A - A kind of autism-spectrum disorder with children ability to cooperate interfering system and method - Google Patents
A kind of autism-spectrum disorder with children ability to cooperate interfering system and method Download PDFInfo
- Publication number
- CN109599162A CN109599162A CN201811358435.8A CN201811358435A CN109599162A CN 109599162 A CN109599162 A CN 109599162A CN 201811358435 A CN201811358435 A CN 201811358435A CN 109599162 A CN109599162 A CN 109599162A
- Authority
- CN
- China
- Prior art keywords
- module
- training
- trainer
- human
- autism
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 208000029560 autism spectrum disease Diseases 0.000 title claims abstract description 14
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 112
- 230000009471 action Effects 0.000 claims abstract description 38
- 230000008569 process Effects 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 11
- 230000033001 locomotion Effects 0.000 claims description 7
- 238000011084 recovery Methods 0.000 claims description 6
- 238000009415 formwork Methods 0.000 claims description 5
- 230000001144 postural effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 206010003805 Autism Diseases 0.000 abstract description 21
- 208000020706 Autistic disease Diseases 0.000 abstract description 21
- 230000003993 interaction Effects 0.000 abstract description 8
- 230000003542 behavioural effect Effects 0.000 abstract 1
- 230000036544 posture Effects 0.000 description 21
- 230000000694 effects Effects 0.000 description 6
- 210000000707 wrist Anatomy 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 201000001880 Sexual dysfunction Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 208000030251 communication disease Diseases 0.000 description 1
- 208000028831 congenital heart disease Diseases 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007472 neurodevelopment Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000036301 sexual development Effects 0.000 description 1
- 231100000872 sexual dysfunction Toxicity 0.000 description 1
- 230000000392 somatic effect Effects 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000004006 stereotypic behavior Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
Abstract
It includes desktop client end, browser end and server end that the present invention, which provides a kind of autism-spectrum disorder with children ability to cooperate interfering system and method, the system,;When trainer uses this system for the first time, by browser end on website register account number, enter training after client is logined successfully with account, entirely trained score is transmitted to server end by the data uploading module after training in desktop client end, trainer can formulate the plan for being suitble to autism children in server end query history training score, guidance person according to score.The present invention is suitable for more people interaction, and the accurate tracing and positioning of energy participates in trained children, and each children's limb action expression of identification of energy efficiently and accurately and gesture are expressed simultaneously.Aspectant ability to cooperate training form is converted to the human-computer interaction form more easily received by autism children to present, the Behavioral training so that autism children cooperate in virtual scene reaches the cooperation awareness of culture autism children, improves ability to cooperate.
Description
Technical field
The invention belongs to the technical field of physiology evaluation and test more particularly to a kind of autism-spectrum disorder with children ability to cooperate are dry
Preheater system and method.
Background technique
Autism-spectrum obstacle (Autism Spectrum Disorder, ASD) is one group with social handicap, language
Communication disorder, interest or scope of activities it is narrow and repeat stereotypic behavior be main core symptom neurodevelopment sexual dysfunction, be
Expand according to the core symptom of typical autism the autism in broad sense of definition.
Ability to cooperate is a kind of relative complex social function, and imitates, common pays attention to and the social performances such as theory of mind
Exist between power and is closely connected.But there are heart defects in these social functions for autistic individuals.And cooperate to be children society
Can sexual development important component, therefore have very important significance to autism children ability training of cooperating.
Human-computer interaction research institute, Carnegie Mellon University had once issued a research report about children for learning mode.Report
Announcement points out that the mode of learning of teaching and game based on body-sensing technology is more effective fruit, more than simple mobile platform game
It is good.The participation of three-dimensional is obtained in idea and in movement using the children of somatosensory device training, it being capable of high fuse information perception
With building Studying Situntion, learning efficiency is higher.
For the educational rehabilitation of autism children, application message supplementary means facilitates children social communication, emotion table
Up to etc. various aspects capability improving.Body-sensing training is applied in the training of autism children's rehabilitation, is in autism rehabilitation education
One big innovation.Currently, there are some problems, such as educational rehabilitation class training resource are deficient in autism educational rehabilitation for body-sensing training
Weary, the education and training quantity being applicable in autism rehabilitation training is few, in the training of few suitable autism children
Hold, lacks effectiveness evaluation mechanism, do not measure the standard of autism children training effect, it can only one people of autism children
The sociability of autism children cannot fundamentally be improved by participating in training, and can not accurately be excluded in the training process
Other people interference.
Summary of the invention
Goal of the invention: lacking evaluation mechanism to overcome in the training of above-mentioned body-sensing, can not allow multiple autism children together
It participates in training and excludes occur the problem of other people interference in the training process, the present invention provides a kind of autism-spectrum disorder with children
Ability to cooperate interfering system and method.
Technical solution: the present invention provides a kind of autism-spectrum disorder with children ability to cooperate interfering system, which includes
Desktop client end, browser end and server end;
The desktop client end includes user log-in block, data uploading module, training content module, action recognition mould
Block;The browser end includes registration module, login module, password recovery module, result queries module;
The registration module, for providing register account number when trainer uses for the first time;
The user log-in block, the trainer for completing for registration are logged in using account at desktop client end;
The training content module, for providing specific task training for the trainer that logins successfully, to trainer into
Row arm postural training, and the data fed back according to action recognition module calculate training score;
The action recognition module for acquiring the training data of trainer, and is converted into the data of training mission needs
Format feeds back to training content module;
The data uploading module, the training score for training content module to be calculated are transmitted to server end;
The login module is logged in browser end using account for trainer;
The password recovery module, resets password in the case where forgetting Password for trainer;
The result queries module, for trainer's query history for being logined successfully in browser end using login module
Score.
Further, the action recognition module includes human tracking module and human action identification module;The human body
Tracking module for identification with tracking human body;The human action identification module is for recognition training person arm in the training process
Posture.
Further, the human action identification module, human tracking module share Kinect sensor, above-mentioned two mould
Block carries out motion capture using Kinect sensor, obtains the depth image data and RGB color number of Kinect sensor capture
According to.
A kind of method of autism-spectrum disorder with children ability to cooperate interfering system, specifically comprises the following steps:
Step 1, trainer is logged in client with register account number, into the training program of training content module;
Step 2, in the arm posture as human action identification module recognition training person in leading portion training mission, and mould is carried out
Plate matching;Arm posture in the template that will match to is arranged to identifiable character string and sends training content module to;
Step 3, training content module is given a mark to above-mentioned character string parsing, and to the performance of this section of training mission, note
Record score;
Step 4, training content module carries out next section of task training content;
Step 5, desktop client end shows the score that whole section of training process records after whole section of task, while data upload
Module incites somebody to action to be distributed to server end.
Further, the template matching is using the static posture recognizer in human action identification module;Benefit
The multiple groups arm posture feature vector angle obtained with human body static posture recognizer, and calculate mean value and establish feature vector angle mould
Plate library;Recycle human body static posture recognizer obtain current trainer arm posture feature vector angle, will with it is current
The smallest template of feature vector angular distance of the arm posture of trainer is as recognition result.
Further, the human tracking module is identified and is tracked human body using multiple target tracking algorithm, before training starts,
Human tracking module assert that human body nearest within sweep of the eye is trainer, acquires height, the shoulder breadth feature of trainer, training
When, and stored, when training, the real-time recognition and tracking trainer of human tracking module, nearest people within the vision
The feature of body and the characteristic matching of storage, matching is consistent to be determined as trainer.
The utility model has the advantages that the present invention, suitable for more people interaction, accurately energy is efficient simultaneously by the trained children of tracing and positioning participation for energy
Accurately identify each children's limb action expression and gesture expression.Aspectant ability to cooperate training form is converted to and is more held
The human-computer interaction form easily received by autism children is presented, so that autism children cooperate in virtual scene, behavior is instructed
Practice, reach the cooperation awareness of culture autism children, improves ability to cooperate.
Detailed description of the invention
Fig. 1 is overall system architecture figure of the invention;
Fig. 2 is desktop client end-rack composition of the present invention;
Fig. 3 is trainer's recognition and tracking flow chart of the invention;
Fig. 4 is server architecture figure of the invention.
Specific embodiment
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.
As shown in Figs. 1-2, the present invention provides a kind of autism-spectrum disorder with children ability to cooperate interfering system, the system packet
Include desktop client end, browser end and server end;
The desktop client end includes user log-in block, data uploading module, training content module, action recognition mould
Block;The browser end includes registration module, login module, password recovery module, result queries module;The registration module is used
Account is registered when providing trainer and using for the first time;The server end includes data interface module, business logic modules, data
Library operation module;
The trainer that the user log-in block is used to complete for registration is logged in using account in client;
The training content module is used to provide specific task training for the trainer logined successfully, carries out to trainer
Arm postural training, and the data fed back according to action recognition module calculate training score;
The action recognition module is used to acquire the training data of trainer, and is converted into the data lattice of training mission needs
Formula feeds back to training content module;
Data uploading module is used to the training score that training content module is calculated being transmitted to server end;
Login module is logged in browser end using account for trainer;
The password recovery module, resets password in the case where forgetting Password for trainer;
Result queries module is used for the trainer's query history score logined successfully in browser end using login module;
The action recognition module includes human tracking module and human action identification module;The human tracking module uses
In identifying and tracking human body, prevent other people from interfering training;The human action identification module is for identification instruction in the training process
White silk person's arm posture.
The human action identification module, human tracking module share Kinect sensor, and above-mentioned two module utilizes
Kinect sensor carries out motion capture, obtains the depth image data and RGB color data of Kinect sensor capture.
In the present embodiment can two trainers complete together;
Training content module includes that traffic guidance training module and cooperation meet two portions of note training module in the present embodiment
Point, the client software of traffic guidance training module uses Winform+Flash, and the client that cooperation connects note training module is soft
Part is using Unity3D as development platform;
Traffic guidance training mission is the somatic sensation television game of a double cooperation, by the cooperation of two people by the vapour of different colours
Vehicle cooperates different movements to connect, and the right is successfully transported to from the left side.Trainer 1 and trainer 2 carry out according to left and right relative position
It distinguishes.The left hand of trainer 1 control one can up and down adjustment angle highway, connect three layers of highway and one layer of highway on the left side,
1 right hand of trainer control one can up and down adjustment angle highway, connect three layers of public affairs of one layer of highway Yu 1 right-hand side of trainer
Road.Trainer 2 is similarly;When game starts, at random from upper, middle and lower layer road, trolley is every for red, blue or yellow trolley
When successfully passing the road of trainer commander, one point is counted to the trainer, while correct prompt animation occurs and encouraging audio.It is right
In coloured section, trolley, which must reach section identical with trolley color and just calculate, correctly to be passed through.If trolley sails to section
End, trainer fails to make correct interaction, and when encountering at the end of one's rope situation, trolley is fallen, whole cooperation failure, trip
Play starts next round.Game design difficulty adjusting, can select according to the ability of different children.It can change trainer
1 frequently changes and color change with the road being connected among trainer 2;
It is music class training game that cooperation, which connects note training mission, with the rhythm of background music, the upper left corner and the upper right corner
Sound equipment have note and fall, the far and near position that note is fallen is random.Two children for participating in training control a ground respectively
On trolley, by the movement of the mobile control trolley of itself, with the basketry of roof it is more as far as possible catch the note to fall down.Instruction
Before white silk game starts, red trolley and white trolley are arranged in a line among road, and trainer is waited to enter.It is introduced into game
The trainer of scope of activities controls red trolley, and the trainer entered afterwards controls white trolley, and trainer is by oneself in activity
The ridden in left or right direction of left and right moving control trolley in range.If midway has trainer to leave scope of activities, trainer control
Trolley return to initial position, do not influence another one trainer continue game.The trainer that scope of activities is left in midway can weigh
Newly enter zone of action, continues current training mission.Cooperation connects note training mission according to the speed of background music rhythm, is divided into
Three different grade of difficulty, note fall frequency difference, and falling speed is different, and the difficulty that fast run reaches double hit is different.
For the interest of Support Training task, different grade of difficulty can choose there are many different background musics;
A kind of method of non-autism-spectrum disorder with children ability to cooperate intervention, specifically comprises the following steps:
Before game starts, controller is acquired the right of control using more people's interaction techniques, and more people's interaction techniques are using first Shen
Please rear control strategy, system identification makes the controller of conventional sign, and controller's control system supervises entire training process;If
After controller leaves Kinect catching range, the control of controller is released, and other users can apply for control system;This implementation
Control is teacher in example;
Step 1, trainer is logged in client with register account number, into the training program of training content module;
Step 2, the arm posture of human action identification module recognition training person 1 and trainer 2, and carry out template matching;
Arm posture in the template that will match to is arranged to identifiable character string and sends training content module to;
Step 3, training content module is given a mark to above-mentioned character string parsing, and to the performance of this section of task, is recorded
Point;
Step 4, training content module adjusts next section of task training content;
Step 5, desktop client end shows the score that whole section of training process records after whole section of task, while data upload
Module incites somebody to action to be distributed to server end.
The training content of ability to cooperate training module actively issues instruction mainly in Flash with Flash in the present embodiment
Communicated between Winform and Flash.When game starts, Flash sends " start " to Winform, when Winform is received
When " start ", start to stretch, Winform gives the processing of Kinect data real-time perfoming when capturing 1 left hand level of trainer
The end Flash sends " 1-1-2 ", three numbers, and centre is separated with "-", the first digit, and " 1 " indicates trainer 1, and " 2 " indicate training
Person 2;Second digit, " 1 " indicate left hand, and " 2 " indicate the right hand;Third digit, " 1 " indicate to be directed toward upper layer road, " 2 " expression direction
Intermediate road, " 3 " indicate to be directed toward underpass highway.After the biography value for receiving the end Winform in Flash, to the character string transmitted
It is parsed according to above-mentioned rule, and next task in adjusting training scene, after entire training whole, Flash
" end " is sent to Winform, and the score data recorded in whole section of training process is sent to the end Winform.Winform
After end receives " end ", stops sending data to Flash, and parse the score data that Flash is sent, then upload result
To server.
The template matching is using the static posture recognizer in human action identification module;Utilize human body static state
The multiple groups arm posture feature vector angle that gesture recognition algorithm obtains, and calculate mean value and establish feature vector Angle formwork library;It is sharp again
The feature vector angle that the arm posture of current trainer is obtained with human body static posture recognizer, by the hand with current trainer
The smallest template of feature vector angular distance of arm posture is as recognition result.
In the present embodiment, five left wrist, left elbow, left shoulder, chest, backbone artis are chosen when handling left side posture, are located
Five right wrist, right elbow, right shoulder, chest, backbone artis are chosen when the posture of reason the right.Utilize KinectV2 adopting with 30 frame per second
Sample rate samples skeleton data.
Skeleton data is first pre-processed, using average filter algorithm to the coordinate of above-mentioned five artis at
Reason regards continuous N number of sampled value as the n times measured value of one skeleton state, then takes the average value of n times as the state
Value, formula are as follows:
Wherein: N takes 6, and every six samplings are arranged and take an average value, Pix, Piy, PizIndicate that the artis of i-th acquisition exists
X, Y, the coordinate on Z axis, i are the number of sampling, 1≤i≤N, PX, Py, PzIndicate the joint of n times acquisition in X, Y, on Z axis
Average coordinates.Basis of the framework information obtained after filtering as feature extraction;
Extract the angle character insensitive to length based on framework information obtained above, thus avoid distance feature for
People's otherness of different high height and long arm.By the half of separate computations in left and right, it is respectively as follows: left wrist and is arrived to left elbow, left elbow to left shoulder, left shoulder
The vector of chest, chest to backbone, right wrist to right elbow, right elbow to right shoulder, right shoulder to chest, chest to backbone vector, specifically
Static posture identification feature vector angle calculation formula it is as follows:
Wherein VIFor left wrist to the vector of left elbow, VjFor the vector V of left elbow to left shoulderIxIt is VICoordinate value in the X direction,
VIyIt is ViCoordinate value in the Y direction, VIzIt is VICoordinate value in z-direction.Vjx、Vjy、VjzIt is V respectivelyjIn X, Y, Z-direction
On coordinate value.Angle 0I-JIt is exactly the feature vector angle value in human body elbow portion.
6 kinds of static postures are identified in the present embodiment;Be respectively as follows: left hand to stretch to upper left side, left hand level is stretched, left hand to
Lower left is stretched, and the right hand is stretched to upper right side, right hand level is stretched, the right hand stretches to the right;Each movement acquires 30 groups of marks
Quasi- action data extracts 30 groups of feature vector angles, then takes its mean value as feature vector Angle formwork library;
The feature vector angle of current action is extracted according to the method that features described above vectorial angle is extracted, respectively left eigenvector angle
With right feature vector angle.Left eigenvector angle is matched with left eigenvector Angle formwork library, right feature vector and Zuo Tezheng
Vectorial angle template library is matched.It will be with the smallest template of current action feature vector angular distance as recognition result, distance meter
Calculate formula, calculation formula are as follows:
Wherein g is g-th of template in template library, and 0 < g≤m, m is template total number in template library, dgIndicate current action
At a distance from the feature sign vectorial angle of g-th of template in feature vector Angle formwork library, n is characterized the dimension of vectorial angle at feature vector angle
Degree, akThe feature vector angle for being k for current action feature vector angle dimension, 1≤k≤n;bgk(0 < g≤m, 1≤i≤n) is g
A template characteristic vectorial angle dimension is the feature vector angle of k.
As shown in figure 3, in entire training process, the human tracking module identified using multiple target tracking algorithm and with
Track human body, whenever having human body to enter Kinect within sweep of the eye, Kinect can distribute a skeleton ID for the human body;As long as should
Human body does not walk out the field range of Kinect, his skeleton ID is remained unchanged;Before training, the nearest skeleton ID of distance Kinect is
Trainer;Human tracking module records height, the shoulder breadth feature of trainer, and is stored, and when training, human tracking module is real
When track training person the feature of nearest human body within the vision and the characteristic matching of storage matched consistent identification
For trainer.If trainer leaves midway;Human tracking module by the height of the skeleton ID of distance Kinect nearest human body,
Shoulder breadth feature is matched with the height of the trainer of record, shoulder breadth feature, assert that the human body is trainer if matching is consistent,
Skeleton ID is updated, trainer is allowed to continue to train, it is inconsistent, wait the trainer left to be added.
Kinect most supports while obtaining the framework information of 6 people in the present embodiment.
The entire server rack composition of this system as shown in Figure 4, there is only data between desktop client end and server end
Access relationships, the view that server end does not control are shown, but are controlled by desktop client end oneself, and server end only provides number
According to interface, at desktop client end --- only two modules of controller and model need to be used in the system of server end, in controller
The HTTP request that desktop desktop client end is sent is received, calls corresponding model, then model return value is packaged into JSON string and is returned
Go back to desktop desktop client end.Browser end is then complete MVC framework, and user's request is sent to controller, and controller dependence is asked
It asks which model selection loads, and data and user instruction is passed into model, model carries out business logic processing and necessity
Storing data operation, different views is selected according to service logic and returns to user, the next step of user is waited to operate.
It is further to note that specific technical features described in the above specific embodiments, in reconcilable situation
Under, it can be combined in any appropriate way.In order to avoid unnecessary repetition, the present invention is to various possible combinations
No further explanation will be given for mode.
Claims (6)
1. a kind of autism-spectrum disorder with children ability to cooperate interfering system, which is characterized in that the system includes desktop client end,
Browser end and server end;
The desktop client end includes user log-in block, data uploading module, training content module, action recognition module;Institute
Stating browser end includes registration module, login module, password recovery module, result queries module;
The registration module, for providing register account number when trainer uses for the first time;
The user log-in block, the trainer for completing for registration are logged in using account at desktop client end;
The training content module carries out hand to trainer for providing specific task training for the trainer logined successfully
Arm postural training, and the data fed back according to action recognition module calculate training score;
The action recognition module for acquiring the training data of trainer, and is converted into the data format of training mission needs,
Feed back to training content module;
The data uploading module, the training score for training content module to be calculated are transmitted to server end;
The login module is logged in browser end using register account number for trainer;
The password recovery module, resets password in the case where forgetting Password for trainer;
The result queries module, for being obtained for the trainer's query history logined successfully in browser end using login module
Point.
2. a kind of autism-spectrum disorder with children ability to cooperate interfering system according to claim 1, which is characterized in that institute
Stating action recognition module includes human tracking module and human action identification module;The human tracking module for identification and with
Track human body;The human action identification module is for recognition training person arm posture in the training process.
3. a kind of autism-spectrum disorder with children ability to cooperate interfering system according to claim 2, which is characterized in that institute
Human action identification module, the shared Kinect sensor of human tracking module are stated, above-mentioned two module utilizes Kinect sensor
Motion capture is carried out, the depth image data and RGB color data of Kinect sensor capture are obtained.
4. a kind of method of autism-spectrum disorder with children ability to cooperate interfering system according to claim 3, feature
It is, specifically comprises the following steps:
Step 1, trainer is logged in client with register account number, into the training program of training content module;
Step 2, in the arm posture as human action identification module recognition training person in leading portion training mission, and template is carried out
Match;Arm posture in the template that will match to is arranged to identifiable character string and sends training content module to;
Step 3, training content module is given a mark to above-mentioned character string parsing, and to the performance of this section of training mission, is recorded
Point;
Step 4, training content module carries out next section of task training content;
Step 5, desktop client end shows the score that whole section of training process records, while data uploading module after whole section of task
It incites somebody to action to be distributed to server end.
5. according to the method described in claim 4, it is characterized by: the template matching is using human action identification module
In static posture recognizer;The multiple groups arm posture feature vector angle obtained using human body static posture recognizer, and
It calculates mean value and establishes feature vector Angle formwork library;Human body static posture recognizer is recycled to obtain the arm appearance of current trainer
The feature vector angle of gesture is tied the smallest template of feature vector angular distance of the arm posture with current trainer as identification
Fruit.
6. method according to claim 4 or 5, it is characterised in that: the human tracking module is calculated using multiple target tracking
Method identification and tracking human body, before training starts, human tracking module assert that human body nearest within sweep of the eye is trainer, acquisition
Height, the shoulder breadth feature of trainer when training, and is stored, when training, the real-time recognition and tracking training of human tracking module
Person, the feature of nearest human body within the vision and the characteristic matching of storage, matching is consistent to be determined as trainer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811358435.8A CN109599162A (en) | 2018-11-15 | 2018-11-15 | A kind of autism-spectrum disorder with children ability to cooperate interfering system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811358435.8A CN109599162A (en) | 2018-11-15 | 2018-11-15 | A kind of autism-spectrum disorder with children ability to cooperate interfering system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109599162A true CN109599162A (en) | 2019-04-09 |
Family
ID=65958596
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811358435.8A Pending CN109599162A (en) | 2018-11-15 | 2018-11-15 | A kind of autism-spectrum disorder with children ability to cooperate interfering system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109599162A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110934599A (en) * | 2019-12-20 | 2020-03-31 | 东南大学 | Method and system for evaluating infant common attention in natural scene |
CN111489808A (en) * | 2020-04-27 | 2020-08-04 | 成都工业学院 | Autism spectrum disorder children rehabilitation training auxiliary system |
CN112466433A (en) * | 2019-08-19 | 2021-03-09 | 陈燕惠 | Four-stage CHEN intervention technology for children tic disorder |
JP7462178B1 (en) | 2022-09-21 | 2024-04-05 | 株式会社バイオネット研究所 | Automatic moving object tracking device, automatic moving object tracking method, and automatic moving object tracking program |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184661A (en) * | 2011-03-17 | 2011-09-14 | 南京大学 | Childhood autism language training system and internet-of-things-based centralized training center |
CN102354349A (en) * | 2011-10-26 | 2012-02-15 | 华中师范大学 | Human-machine interaction multi-mode early intervention system for improving social interaction capacity of autistic children |
CN107180235A (en) * | 2017-06-01 | 2017-09-19 | 陕西科技大学 | Human action recognizer based on Kinect |
-
2018
- 2018-11-15 CN CN201811358435.8A patent/CN109599162A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184661A (en) * | 2011-03-17 | 2011-09-14 | 南京大学 | Childhood autism language training system and internet-of-things-based centralized training center |
CN102354349A (en) * | 2011-10-26 | 2012-02-15 | 华中师范大学 | Human-machine interaction multi-mode early intervention system for improving social interaction capacity of autistic children |
CN107180235A (en) * | 2017-06-01 | 2017-09-19 | 陕西科技大学 | Human action recognizer based on Kinect |
Non-Patent Citations (1)
Title |
---|
李杨韬: "基于手势识别的认知训练系统研制", 《中国硕士学位论文电子期刊 基础科学》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112466433A (en) * | 2019-08-19 | 2021-03-09 | 陈燕惠 | Four-stage CHEN intervention technology for children tic disorder |
CN110934599A (en) * | 2019-12-20 | 2020-03-31 | 东南大学 | Method and system for evaluating infant common attention in natural scene |
CN111489808A (en) * | 2020-04-27 | 2020-08-04 | 成都工业学院 | Autism spectrum disorder children rehabilitation training auxiliary system |
JP7462178B1 (en) | 2022-09-21 | 2024-04-05 | 株式会社バイオネット研究所 | Automatic moving object tracking device, automatic moving object tracking method, and automatic moving object tracking program |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109599162A (en) | A kind of autism-spectrum disorder with children ability to cooperate interfering system and method | |
CA3146658A1 (en) | Interactive personal training system | |
CN110739040A (en) | rehabilitation evaluation and training system for upper and lower limbs | |
CN106880927A (en) | Run and integrate store exchanging device, system and method | |
CN104766503A (en) | cardiopulmonary resuscitation teaching system and method | |
CN107293175A (en) | A kind of locomotive hand signal operation training method based on body-sensing technology | |
CN113144540A (en) | Intelligent safe fitness guidance device, system and method | |
CN105832502A (en) | Intelligent visual function training method and instrument | |
CN107670261A (en) | A kind of internet motion assistant system based on motion capture technology | |
CN109543652A (en) | A kind of wisdom ski training device and its training result display methods, Cloud Server | |
Tsangouri et al. | An interactive facial-expression training platform for individuals with autism spectrum disorder | |
TW201121614A (en) | Digital contents based on integration of virtual objects and real image | |
CN109003139A (en) | A kind of Cultural Square system and method for supporting intelligent interaction | |
Huang et al. | Miss yoga: a yoga assistant mobile application based on keypoint detection | |
Ma et al. | Development of the Interactive Rehabilitation Game System for Children with Autism Based on Game Psychology | |
Hsieh et al. | A distance computer vision assisted yoga learning system | |
WO2022034771A1 (en) | Program, method, and information processing device | |
Hou et al. | RETRACTED ARTICLE: An auxiliary training system for swimming in coastal areas based on remote sensing images and virtual simulation technology | |
JP6884306B1 (en) | System, method, information processing device | |
Jiang et al. | Design and research of vr basketball teaching system based on embedded intelligent sensor | |
CN116271757A (en) | Auxiliary system and method for basketball practice based on AI technology | |
CN215231970U (en) | Intelligent safety body-building guiding device | |
Wang et al. | Intelligent somatosensory interactive activities restore motor function to children with autism | |
CN115985462A (en) | Rehabilitation and intelligence-developing training system for children cerebral palsy | |
Su | Artificial intelligence in the auxiliary guidance function of athletes’ movement standard training in physical education |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
RJ01 | Rejection of invention patent application after publication |